Kun Zhang

Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards ACL 2026 FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation ACL 2026 Horizontal and Vertical Federated Causal Structure Learning via Higher-order Cumulants AAAI 2026 Identifying Weight-Variant Latent Causal Models JMLR 2026 Learning by Analogy: A Causal Framework for Compositional Generalization CVPR 2026 Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and Beyond AAAI 2026 Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism CVPR 2026 Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-Based Test Oracles AAAI 2026 A Conditional Independence Test in the Presence of Discretization ICLR 2025 A General Knowledge Injection Framework for ICD Coding ACL 2025 A General Representation-Based Approach to Multi-Source Domain Adaptation ICML 2025 Analytic DAG Constraints for Differentiable DAG Learning ICLR 2025 A Robust Method to Discover Causal or Anticausal Relation ICLR 2025 A Sample Efficient Conditional Independence Test in the Presence of Discretization ICML 2025 A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery ICLR 2025 Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference ICLR 2025 Causal Representation Learning from General Environments under Nonparametric Mixing AISTATS 2025 Causal Representation Learning from Multimodal Biomedical Observations ICLR 2025 Continual Unsupervised Generative Modelling via Online Optimal Transport AAAI 2025 DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning CVPR 2025 Differentiable Causal Discovery for Latent Hierarchical Causal Models ICLR 2025 DiffRGenNet: Difference-aware Medical Report Generation MIDL 2025 Dynamic Expansion Diffusion Learning for Lifelong Generative Modelling AAAI 2025 Empowering LLMs with Logical Reasoning: A Comprehensive Survey IJCAI 2025 Extracting Rare Dependence Patterns via Adaptive Sample Reweighting ICML 2025 Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness ICML 2025 Flow: Modularized Agentic Workflow Automation ICLR 2025 Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval ICCV 2025 Identification of Intermittent Temporal Latent Process ICLR 2025 Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations ICML 2025 Latent Variable Causal Discovery under Selection Bias ICML 2025 Learning Graph Invariance by Harnessing Spuriosity ICLR 2025 Learning Vision and Language Concepts for Controllable Image Generation ICML 2025 MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning ACL 2025 MVP-CBM: Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification IJCAI 2025 Noisy Test-Time Adaptation in Vision-Language Models ICLR 2025 Nonparametric Factor Analysis and Beyond AISTATS 2025 Nonparametric Identification of Latent Concepts ICML 2025 OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad CVPR 2025 On the Identification of Temporal Causal Representation with Instantaneous Dependence ICLR 2025 Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data ICML 2025 Prompting Fairness: Integrating Causality to Debias Large Language Models ICLR 2025 Reflection-Window Decoding: Text Generation with Selective Refinement ICML 2025 SmartCLIP: Modular Vision-language Alignment with Identification Guarantees CVPR 2025 Structured Discourse Representation for Factual Consistency Verification ACL 2025 Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning ICLR 2025 TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding EMNLP 2025 Type Information-Assisted Self-Supervised Knowledge Graph Denoising AISTATS 2025 Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models ACL 2025 Voices of Her: Analyzing Gender Differences in the AI Publication World ACL 2025 When Selection Meets Intervention: Additional Complexities in Causal Discovery ICLR 2025 ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation AAAI 2024 A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs NeurIPS 2024 A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables ICLR 2024 CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process ICML 2024 Causal-learn: Causal Discovery in Python JMLR 2024 Causal Representation Learning from Multiple Distributions: A General Setting ICML 2024 Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions ICLR 2024 Causal Temporal Representation Learning with Nonstationary Sparse Transition NeurIPS 2024 Detecting and Identifying Selection Structure in Sequential Data ICML 2024 Discovery of the Hidden World with Large Language Models NeurIPS 2024 Empowering Graph Invariance Learning with Deep Spurious Infomax ICML 2024 Federated Causal Discovery from Heterogeneous Data ICLR 2024 Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables JMLR 2024 Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View ICLR 2024 Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations JMLR 2024 Identifiable Latent Polynomial Causal Models through the Lens of Change ICLR 2024 Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants AAAI 2024 Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching AAAI 2024 Identifying Latent State-Transition Processes for Individualized Reinforcement Learning NeurIPS 2024 Identifying Selections for Unsupervised Subtask Discovery NeurIPS 2024 Learning Discrete Concepts in Latent Hierarchical Models NeurIPS 2024 Learning Discrete Latent Variable Structures with Tensor Rank Conditions NeurIPS 2024 LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer ICLR 2024 Local Causal Discovery with Linear non-Gaussian Cyclic Models AISTATS 2024 Natural Counterfactuals With Necessary Backtracking NeurIPS 2024 Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization NeurIPS 2024 On Causal Discovery in the Presence of Deterministic Relations NeurIPS 2024 On the Parameter Identifiability of Partially Observed Linear Causal Models NeurIPS 2024 On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data ICML 2024 Optimal Kernel Choice for Score Function-based Causal Discovery ICML 2024 Procedural Fairness Through Decoupling Objectionable Data Generating Components ICLR 2024 S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment AAAI 2024 Score-Based Causal Discovery of Latent Variable Causal Models ICML 2024 Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability ICLR 2024 Structure Learning with Continuous Optimization: A Sober Look and Beyond CLeaR 2024 Towards Understanding Extrapolation: a Causal Lens NeurIPS 2024 Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models AAAI 2024 Visual-Linguistic Dependency Encoding for Image-Text Retrieval COLING 2024 Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems ICLR 2023 Causal Balancing for Domain Generalization ICLR 2023 Causal Discovery with Latent Confounders Based on Higher-Order Cumulants ICML 2023 Causal Discovery with Score Matching on Additive Models with Arbitrary Noise CLeaR 2023 Counterfactual Generation with Identifiability Guarantees NeurIPS 2023 Disentangling Cognitive Diagnosis with Limited Exercise Labels NeurIPS 2023 Evolving Semantic Prototype Improves Generative Zero-Shot Learning ICML 2023 FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation EMNLP 2023 Fair Representation Learning for Recommendation: A Mutual Information Perspective AAAI 2023 Feature Expansion for Graph Neural Networks ICML 2023 GAIN: On the Generalization of Instructional Action Understanding ICLR 2023 Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks ICLR 2023 Generalizing Nonlinear ICA Beyond Structural Sparsity NeurIPS 2023 Identifiability of Label Noise Transition Matrix ICML 2023 Identification of Nonlinear Latent Hierarchical Models NeurIPS 2023 Learning World Models with Identifiable Factorization NeurIPS 2023 Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract) AAAI 2023 Model Transferability with Responsive Decision Subjects ICML 2023 Multi-domain image generation and translation with identifiability guarantees ICLR 2023 On the Identifiability of Sparse ICA without Assuming Non-Gaussianity NeurIPS 2023 PLOT: Prompt Learning with Optimal Transport for Vision-Language Models ICLR 2023 ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation EMNLP 2023 Scalable Causal Discovery with Score Matching CLeaR 2023 SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model CVPR 2023 Subspace Identification for Multi-Source Domain Adaptation NeurIPS 2023 Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer ICCV 2023 Temporally Disentangled Representation Learning under Unknown Nonstationarity NeurIPS 2023 Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors ICLR 2023 Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction ACL 2023 Understanding Masked Autoencoders via Hierarchical Latent Variable Models CVPR 2023 Unpaired Image-to-Image Translation With Shortest Path Regularization CVPR 2023 Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction CVPR 2023 Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise? ICML 2023 Action-Sufficient State Representation Learning for Control with Structural Constraints ICML 2022 AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning ICLR 2022 Adversarial Robustness Through the Lens of Causality ICLR 2022 Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint CVPR 2022 Attainability and Optimality: The Equalized Odds Fairness Revisited CLeaR 2022 Causal Discovery in Linear Latent Variable Models Subject to Measurement Error NeurIPS 2022 CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing EMNLP 2022 Conditional Contrastive Learning with Kernel ICLR 2022 Counterfactual Fairness with Partially Known Causal Graph NeurIPS 2022 Factored Adaptation for Non-Stationary Reinforcement Learning NeurIPS 2022 GLaM: Efficient Scaling of Language Models with Mixture-of-Experts ICML 2022 Identification of Linear Latent Variable Model with Arbitrary Distribution AAAI 2022 Identification of Linear Non-Gaussian Latent Hierarchical Structure ICML 2022 Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis ACL 2022 Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models NeurIPS 2022 Invariant Action Effect Model for Reinforcement Learning AAAI 2022 Latent Hierarchical Causal Structure Discovery with Rank Constraints NeurIPS 2022 Learning Temporally Causal Latent Processes from General Temporal Data ICLR 2022 Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation CVPR 2022 Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases COLING 2022 MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models NeurIPS 2022 Negative-Aware Attention Framework for Image-Text Matching CVPR 2022 On the Convergence of Continuous Constrained Optimization for Structure Learning AISTATS 2022 On the Identifiability of Nonlinear ICA: Sparsity and Beyond NeurIPS 2022 Optimal Transport for Causal Discovery ICLR 2022 Partial disentanglement for domain adaptation ICML 2022 Residual Similarity Based Conditional Independence Test and Its Application in Causal Discovery AAAI 2022 Show Your Faith: Cross-Modal Confidence-Aware Network for Image-Text Matching AAAI 2022 Temporally Disentangled Representation Learning NeurIPS 2022 Towards Federated Bayesian Network Structure Learning with Continuous Optimization AISTATS 2022 Truncated Matrix Power Iteration for Differentiable DAG Learning NeurIPS 2022 Unsupervised Image-to-Image Translation with Density Changing Regularization NeurIPS 2022 K^2-GNN: Multiple Users’ Comments Integration with Probabilistic K-Hop Knowledge Graph Neural Networks ACML 2021 DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis ICCV 2021 DeepTrader: A Deep Reinforcement Learning Approach for Risk-Return Balanced Portfolio Management with Market Conditions Embedding AAAI 2021 Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? NeurIPS 2021 Identification of Partially Observed Linear Causal Models: Graphical Conditions for the Non-Gaussian and Heterogeneous Cases NeurIPS 2021 Ideography Leads Us to the Field of Cognition: A Radical-Guided Associative Model for Chinese Text Classification AAAI 2021 Improving Causal Discovery By Optimal Bayesian Network Learning AAAI 2021 Instance-dependent Label-noise Learning under a Structural Causal Model NeurIPS 2021 Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching AAAI 2021 Progressive Open-Domain Response Generation with Multiple Controllable Attributes IJCAI 2021 Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions NeurIPS 2021 Testing Independence Between Linear Combinations for Causal Discovery AAAI 2021 Unaligned Image-to-Image Translation by Learning to Reweight ICCV 2021 A Causal View on Robustness of Neural Networks NeurIPS 2020 Causal Discovery from Heterogeneous/Nonstationary Data JMLR 2020 Causal Discovery from Multiple Data Sets with Non-Identical Variable Sets AAAI 2020 Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs ICML 2020 Compressed Self-Attention for Deep Metric Learning AAAI 2020 Domain Adaptation as a Problem of Inference on Graphical Models NeurIPS 2020 Gated Convolutional Networks with Hybrid Connectivity for Image Classification AAAI 2020 Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs NeurIPS 2020 Generative-Discriminative Complementary Learning AAAI 2020 How do fair decisions fare in long-term qualification? NeurIPS 2020 Label-Noise Robust Domain Adaptation ICML 2020 Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables JMLR 2020 LTF: A Label Transformation Framework for Correcting Label Shift ICML 2020 On the Role of Sparsity and DAG Constraints for Learning Linear DAGs NeurIPS 2020 PIDS: An Intelligent Electric Power Management Platform AAAI 2020 Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach AAAI 2020 Re-Weighted Interval Loss for Handling Data Imbalance Problem of End-to-End Keyword Spotting Interspeech 2020 Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models ICML 2019 Causal Discovery in the Presence of Missing Data AISTATS 2019 Causal Discovery with Cascade Nonlinear Additive Noise Model IJCAI 2019 Causal Discovery with General Non-Linear Relationships using Non-Linear ICA UAI 2019 Counting and Sampling from Markov Equivalent DAGs Using Clique Trees AAAI 2019 Data-Driven Approach to Multiple-Source Domain Adaptation AISTATS 2019 Domain Generalization via Multidomain Discriminant Analysis UAI 2019 DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching AAAI 2019 Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping CVPR 2019 Intelligent Decision Support for Improving Power Management IJCAI 2019 Learning Disentangled Semantic Representation for Domain Adaptation IJCAI 2019 Likelihood-Free Overcomplete ICA and Applications In Causal Discovery NeurIPS 2019 Low-Dimensional Density Ratio Estimation for Covariate Shift Correction AISTATS 2019 Neural News Recommendation with Long- and Short-term User Representations ACL 2019 Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation NeurIPS 2019 On Learning Invariant Representations for Domain Adaptation ICML 2019 Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering NeurIPS 2019 Triad Constraints for Learning Causal Structure of Latent Variables NeurIPS 2019 Twin Auxilary Classifiers GAN NeurIPS 2019 Causal Discovery from Discrete Data using Hidden Compact Representation NeurIPS 2018 Deep Domain Generalization via Conditional Invariant Adversarial Networks ECCV 2018 Modeling Dynamic Missingness of Implicit Feedback for Recommendation NeurIPS 2018 Multi-domain Causal Structure Learning in Linear Systems NeurIPS 2018 Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination IJCAI 2017 Learning Causal Structures Using Regression Invariance NeurIPS 2017 Domain Adaptation with Conditional Transferable Components ICML 2016 Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components ICML 2015 Discovering Temporal Causal Relations from Subsampled Data ICML 2015 Identification of Time-Dependent Causal Model: A Gaussian Process Treatment IJCAI 2015 Domain Adaptation under Target and Conditional Shift ICML 2013 Causal discovery with scale-mixture model for spatiotemporal variance dependencies NeurIPS 2012 A General Linear Non-Gaussian State-Space Model: Identifiability, Identification, and Applications ACML 2011 Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity JMLR 2010 Probabilistic latent variable models for distinguishing between cause and effect NeurIPS 2010 Minimal Nonlinear Distortion Principle for Nonlinear Independent Component Analysis JMLR 2008